As I pointed out in my previous blog, the TDSP lifecycle is made up of five iterative stages:
- Business Understanding
- Data Acquisition and Understanding
- Modeling
- Deployment
- Customer Acceptance
This is not very different from the six major phases used by the Cross Industry Standard Process for Data Mining (“CRISP-DM”). The process diagram for CRISP-DM looks like this:
Image from Data Science Central : http://bit.ly/2HGwYzP
The process diagram for TDSP is this:
Diagram from Microsoft: http://bit.ly/2BRbbUo
In both cases you have repeatable steps that, when followed, bring you ever closer to understanding your data. If you are already familiar with one, and your team is used to using that lifecycle, you can continue to use it within the TDSP environment where you have access to machine learning, AI models, templates, scripts, storage, communication tools, version control, storage, all the raw horsepower you may need, and so much more, to make the execution along any lifecycle quicker, easier and consistent.
Within each stage of the TDSP Lifecycle, Microsoft provides you with sample goals, instructions on how to tackle specific tasks within that stage, and artifacts to help you design and produce deliverables.
In my next blog, I will start the process of describing each step of the lifecycle.
